def createLocationObservation(iesGraph,mmsi,timestamp,lat,lon,obs=None):
print(mmsi,timestamp)
#add the location transponder - We don't know this is necessarily a vessel. All we know is that we have a LocationTransponder.
lt = createLocationTransponder(iesGraph=iesGraph,mmsi=mmsi)
#Now create the observation event
lo = instantiate(iesGraph=iesGraph,_class=locationObservation)
#If track emulation is not required, obs will be None. If it's not None, make the LocationObservation (lo) part of the overall track observation
if obs:
addToGraph(iesGraph=iesGraph,subject=lo,predicate=ipao,obj=obs)
#...and the ParticularPeriod in which the observation occurred
putInPeriod(iesGraph=iesGraph,item=lo,iso8601TimeString=timestamp)
#And involve the transponder in that location observation
ltPart = instantiate(iesGraph=iesGraph,_class=observedTarget)
addToGraph(iesGraph=iesGraph,subject=ltPart,predicate=ipo,obj=lt) #participation of the transponder
addToGraph(iesGraph=iesGraph,subject=ltPart,predicate=ipi,obj=lo) #participation in the LocationObservation
#Now the observed location, a geopoint with a lat and long - using a geohash to give each point a unique uri
gp = URIRef(dataUri+"geohash_"+Geohash.encode(lat,lon))
instantiate(iesGraph=iesGraph,_class=geoPoint,instance=gp)
#Add the lat and long values as identifiers of the geopoint...firstly creating repeatable URIs for them so they don't overwrite
latObj = URIRef(gp.toPython()+"_lat")
lonObj = URIRef(gp.toPython()+"_lon")
instantiate(iesGraph=iesGraph, _class=latitude,instance=latObj)
instantiate(iesGraph=iesGraph, _class=longitude,instance=lonObj)
addToGraph(iesGraph=iesGraph,subject=gp,predicate=iib,obj=latObj)
addToGraph(iesGraph=iesGraph,subject=gp,predicate=iib,obj=lonObj)
#Add the representation values to the lat and lon objects
addToGraph(iesGraph=iesGraph,subject=latObj,predicate=rv,obj=Literal(lat, datatype=XSD.string))
addToGraph(iesGraph=iesGraph,subject=lonObj,predicate=rv,obj=Literal(lon, datatype=XSD.string))
#Now the participation of the GeoPoint in the Observation
gpPart = instantiate(iesGraph=iesGraph,_class=observedLocation)
addToGraph(iesGraph=iesGraph,subject=gpPart,predicate=ipo,obj=gp) #participation of the GeoPoint
addToGraph(iesGraph=iesGraph,subject=gpPart,predicate=ipi,obj=lo) #participation in the LocationObservation
def frequency_from_rdf(term):
if isinstance(term, str):
try:
term = URIRef(uris.validate(term))
except uris.ValidationError:
pass
if isinstance(term, Literal):
if term.toPython() in UPDATE_FREQUENCIES:
return term.toPython()
if isinstance(term, RdfResource):
term = term.identifier
if isinstance(term, URIRef):
if EUFREQ in term:
return EU_RDF_REQUENCIES.get(term)
_, _, freq = namespace_manager.compute_qname(term)
return freq
def duration(value, df):
event_uris = df['uri']
unit = 'hour'
datetime_now = datetime.utcnow().replace(tzinfo=tz.tzutc()).astimezone(
tz.tzlocal())
datum_uri = URIRef('{}{}'.format(
ns,
md5('{}{}'.format(datetime_now, 'datum').encode()).hexdigest()))
arithmetic_mean_calculation_uri = URIRef('{}{}'.format(
ns,
md5('{}{}'.format(
datetime_now,
'arithmetic_mean_calculation').encode()).hexdigest()))
dataset_uri = URIRef('{}{}'.format(
ns,
md5('{}{}'.format(datetime_now, 'dataset').encode()).hexdigest()))
g.add((obo['atmospheric aerosol formation event'], RDFS.label,
Literal('atmospheric aerosol formation event')))
g.add((obo['scalar measurement datum'], RDFS.label,
Literal('scalar measurement datum')))
g.add((obo['has measurement unit label'], RDFS.label,
Literal('has measurement unit label')))
g.add((obo['has measurement value'], RDFS.label,
Literal('has measurement value')))
g.add((obo['time unit'], RDFS.label, Literal('time unit')))
g.add((obo['hour'], RDFS.label, Literal('hour')))
g.add((obo['average value'], RDFS.label, Literal('average value')))
g.add((obo['is_specified_output_of'], RDFS.label,
Literal('is_specified_output_of')))
g.add((obo['has_specified_output'], RDFS.label,
Literal('has_specified_output')))
g.add((obo['arithmetic mean calculation'], RDFS.label,
Literal('arithmetic mean calculation')))
g.add((obo['has_specified_input'], RDFS.label,
Literal('has_specified_input')))
g.add((obo['data set'], RDFS.label, Literal('data set')))
g.add((obo['has part'], RDFS.label, Literal('has part')))
g.add((obo['data item'], RDFS.label, Literal('data item')))
g.add((obo['hour'], RDF.type, obo['time unit']))
g.add((arithmetic_mean_calculation_uri, RDF.type,
obo['arithmetic mean calculation']))
g.add((dataset_uri, RDF.type, obo['data set']))
g.add((datum_uri, RDF.type, obo['scalar measurement datum']))
g.add((datum_uri, RDF.type, obo['average value']))
g.add((datum_uri, RDF.type, orkg['ResearchResult']))
g.add((datum_uri, obo['is about'],
obo['atmospheric aerosol formation event']))
g.add((datum_uri, obo['has measurement value'],
Literal(value, datatype=XSD.decimal)))
g.add((datum_uri, obo['has measurement unit label'], obo['hour']))
g.add((datum_uri, obo['is_specified_output_of'],
arithmetic_mean_calculation_uri))
g.add((arithmetic_mean_calculation_uri, obo['has_specified_output'],
datum_uri))
g.add((arithmetic_mean_calculation_uri, obo['has_specified_input'],
dataset_uri))
for event_uri in event_uris:
g.add((URIRef(event_uri), RDF.type, obo['data item']))
g.add((dataset_uri, obo['has part'], URIRef(event_uri)))
g.add((dataset_uri, RDF.type, prov['Entity']))
g.add((datum_uri, RDF.type, prov['Entity']))
g.add((arithmetic_mean_calculation_uri, RDF.type, prov['Activity']))
g.add((datum_uri, prov['wasDerivedFrom'], dataset_uri))
g.add((datum_uri, prov['wasGeneratedBy'], arithmetic_mean_calculation_uri))
g.add((arithmetic_mean_calculation_uri, prov['used'], dataset_uri))
g.add((arithmetic_mean_calculation_uri, prov['startedAtTime'],
Literal(datetime_now.isoformat(), datatype=XSD.dateTime)))
g.add((arithmetic_mean_calculation_uri, prov['endedAtTime'],
Literal(datetime_now.isoformat(), datatype=XSD.dateTime)))
return datum_uri.toPython()
def createLocationObservation(iesGraph,
ping,
obs=None,
transponder=None,
measures=None):
mmsi = str(ping[0])
timestamp = str(ping[1])
lat = float(ping[2])
lon = float(ping[3])
print(lat, lon)
if transponder == None:
transponder = ies.createLocationTransponder(iesGraph=iesGraph,
mmsi=mmsi)
lo = ies.instantiate(iesGraph=iesGraph, _class=ies.locationObservation)
#If track emulation is not required, obs will be None. If it's not None, make the LocationObservation (lo) part of the overall track observation
if obs:
ies.addToGraph(iesGraph=iesGraph,
subject=lo,
predicate=ies.ipao,
obj=obs)
#...and the ParticularPeriod in which the observation occurred
ies.putInPeriod(iesGraph=iesGraph, item=lo, timeString=timestamp)
#And involve the transponder in that location observation
ltPart = ies.instantiate(iesGraph=iesGraph, _class=ies.observedTarget)
ies.addToGraph(iesGraph=iesGraph,
subject=ltPart,
predicate=ies.ipo,
obj=transponder) #participation of the transponder
ies.addToGraph(iesGraph=iesGraph,
subject=ltPart,
predicate=ies.ipi,
obj=lo) #participation in the LocationObservation
#Now the observed location, a geopoint with a lat and long - using a geohash to give each point a unique uri
gp = URIRef(ies.dataUri + "latlong" + str(lat) + "," + str(lon))
ies.instantiate(iesGraph=iesGraph, _class=ies.geoPoint, instance=gp)
#Add the lat and long values as identifiers of the geopoint...firstly creating repeatable URIs for them so they don't overwrite
latObj = URIRef(gp.toPython() + "_lat")
lonObj = URIRef(gp.toPython() + "_lon")
ies.instantiate(iesGraph=iesGraph, _class=ies.latitude, instance=latObj)
ies.instantiate(iesGraph=iesGraph, _class=ies.longitude, instance=lonObj)
ies.addToGraph(iesGraph=iesGraph,
subject=gp,
predicate=ies.iib,
obj=latObj)
ies.addToGraph(iesGraph=iesGraph,
subject=gp,
predicate=ies.iib,
obj=lonObj)
#Add the representation values to the lat and lon objects
ies.addToGraph(iesGraph=iesGraph,
subject=latObj,
predicate=ies.rv,
obj=Literal(lat, datatype=XSD.string))
ies.addToGraph(iesGraph=iesGraph,
subject=lonObj,
predicate=ies.rv,
obj=Literal(lon, datatype=XSD.string))
#Now the participation of the GeoPoint in the Observation
gpPart = ies.instantiate(iesGraph=iesGraph, _class=ies.observedLocation)
ies.addToGraph(iesGraph=iesGraph,
subject=gpPart,
predicate=ies.ipo,
obj=gp) #participation of the GeoPoint
ies.addToGraph(iesGraph=iesGraph,
subject=gpPart,
predicate=ies.ipi,
obj=lo) #participation in the LocationObservation
#This code fires if the measure classes etc. have been provided - it takes the speed and course over ground and processes that.
if measures:
sogVal = float(ping[4])
cogVal = float(ping[5])
sog = ies.addMeasure(iesGraph=iesGraph,
measureClass=measures["sogClass"],
value=sogVal,
uom=measures["knots"])
cog = ies.addMeasure(iesGraph=iesGraph,
measureClass=measures["cogClass"],
value=cogVal,
uom=measures["degTN"])
ies.addToGraph(iesGraph=iesGraph,
subject=ltPart,
predicate=ies.och,
obj=sog)
ies.addToGraph(iesGraph=iesGraph,
subject=ltPart,
predicate=ies.och,
obj=cog)
def would_you_like_to_know_more_question_mark():
# resolving differences between classes
more_ids = set((
'http://uri.neuinfo.org/nif/nifstd/readable/ChEBIid',
'http://uri.neuinfo.org/nif/nifstd/readable/GOid',
'http://uri.neuinfo.org/nif/nifstd/readable/MeshUid',
'http://uri.neuinfo.org/nif/nifstd/readable/PMID',
'http://uri.neuinfo.org/nif/nifstd/readable/UmlsCui',
'http://uri.neuinfo.org/nif/nifstd/readable/bamsID',
'http://uri.neuinfo.org/nif/nifstd/readable/bonfireID',
'http://uri.neuinfo.org/nif/nifstd/readable/cell_ontology_ID',
'http://uri.neuinfo.org/nif/nifstd/readable/definingCitationID',
'http://uri.neuinfo.org/nif/nifstd/readable/definingCitationURI',
'http://uri.neuinfo.org/nif/nifstd/readable/emapMouseStageDataID',
'http://uri.neuinfo.org/nif/nifstd/readable/emapMouseStageDiagramID',
'http://uri.neuinfo.org/nif/nifstd/readable/externalSourceId',
'http://uri.neuinfo.org/nif/nifstd/readable/externalSourceURI',
'http://uri.neuinfo.org/nif/nifstd/readable/gbifID',
'http://uri.neuinfo.org/nif/nifstd/readable/gbifTaxonKeyID',
'http://uri.neuinfo.org/nif/nifstd/readable/gene_Ontology_ID',
#'http://uri.neuinfo.org/nif/nifstd/readable/hasExternalSource',
'http://uri.neuinfo.org/nif/nifstd/readable/hasGenbankAccessionNumber',
'http://uri.neuinfo.org/nif/nifstd/readable/imsrStandardStrainName',
'http://uri.neuinfo.org/nif/nifstd/readable/isReplacedByClass',
'http://uri.neuinfo.org/nif/nifstd/readable/jaxMiceID',
'http://uri.neuinfo.org/nif/nifstd/readable/ncbiTaxID',
'http://uri.neuinfo.org/nif/nifstd/readable/neuronamesID',
'http://uri.neuinfo.org/nif/nifstd/readable/nifID',
'http://uri.neuinfo.org/nif/nifstd/readable/sao_ID',
'http://uri.neuinfo.org/nif/nifstd/readable/umls_ID',
'http://www.geneontology.org/formats/oboInOwl#id',
))
outside = []
eee = {}
resolver_not_ilx_only_but_not_in_scigraph = set() # resources.ttl
_res = Graph().parse((gitf / 'NIF-Ontology/ttl/resources.ttl').as_posix(), format='turtle')
reslookup = {uri:[l] for uri, l in _res.subject_objects(rdfs.label)}
for uri in chain(h_uris, resolver_not_ilx_only):
if 'uri.neuinfo.org' in uri:
try:
meta = sgg.getNode(uri.toPython())['nodes'][0]['meta']
asdf = {hng.qname(k):v for k, v in meta.items() if k in more_ids}
except TypeError:
resolver_not_ilx_only_but_not_in_scigraph.add(uri) # resources.ttl ;)
if uri in reslookup: # no differentia
asdf = False
else:
asdf = False
print('WTF', uri)
if asdf:
#print(uri, asdf)
eee[uri] = asdf
for l in asdf.values():
for e in l:
outside.append(e)
outside_dupes = [v for v, c in Counter(outside).most_common() if c > 1]
eee_dupes = {k:v for k, v in eee.items() if anyMembers(outside_dupes, *(e for l in v.values() for e in l))}
#for uri, meta in sorted(eee_dupes.items(), key=lambda a:sorted(a[1].values())):
#print(uri.toPython(), sorted((e.replace('PMID: ', 'PMID:'), k) for k, l in meta.items() for e in l))
# attempt to deal with label mappings
iexisting = defaultdict(set)
iiexisting = {}
for i, existing in zip(datal('ilx'), datal('iri')):
#if 'uri.neuinfo.org' in existing:
if 'interlex.org' not in existing and 'neurolex.org' not in existing:
iexisting[i].add(URIRef(existing))
iiexisting[URIRef(existing)] = i
iexisting = {**iexisting}
_ilabs = {k:l for k, l in zip(datal('ilx'), datal('label'))}
def inner(iri):
resp = sgv.findById(iri)
if resp is not None:
l = resp['labels']
else:
l = [] #_ilabs[iiexisting[iri]] + '** already in ilx **']
#print('trouble?', iri) # ilx only
return iri, l
#labs = {k:v[0] if v else '<--NO-LABEL-->' for k, v in Async()(deferred(inner)(id_) for id_ in chain(h_uris, (e for s in iexisting.values() for e in s)))}
labs = {k:v[0] if v else '<--NO-LABEL-->' for k, v in Async()(deferred(inner)(id_) for id_ in h_uris)}
ilabs = {k:l.lower() for k, l in zip(datal('ilx'), datal('label'))}
iilabs = {v:k for k, v in ilabs.items()}
assert len(ilabs) == len(iilabs)
missing_map = {k:iilabs[v.lower()] for k, v in labs.items() if v and v.lower() in iilabs} # XXX this is not valid
missing_existing = {i:[m, *iexisting[i]] for m, i in missing_map.items() if i in iexisting}
missing_equivs = {next(iter(iexisting[i])):i for m, i in missing_map.items() if i in iexisting}
eid = NIFRID.externalSourceId.toPython()
ded = owl.deprecated.toPython()
# SP: -> swissprot vs uniprot
mmr = []
proto_mmr_1_to_1 = {}
arrr = defaultdict(set)
uniprot_iuphar = set()
for uri, ilx_frag in {**missing_equivs, **missing_map}.items():
uri = URIRef(uri)
try:
meta = sgg.getNode(uri.toPython())['nodes'][0]['meta']
except TypeError:
# just ignore these, they are ilx only :/
meta = {}
if eid in meta:
src = meta[eid][0]
if src.startswith('SP:'):
src = tc.yellow(src.replace('SP:', 'http://www.uniprot.org/uniprot/'))
#elif src.startswith('IUPHAR:'):
#pass
#else:
#src = 'TODO'
elif ded in meta and meta[ded]:
src = tc.red('ded ')
else:
src = 'TODO'
val = labs[uri] if uri in labs else _ilabs[ilx_frag] + ' **'
if uri in eee:
differentia = str(eee[uri])
for v in eee[uri].values():
for e in v:
arrr[e].add(uri)
if 'SP:' in e or 'IUPHAR:' in e:
uniprot_iuphar.add(uri)
else:
differentia = ''
if uri in _ilx and uri in all_uris:
ruri = SGG[hng.qname(uri)]
ruri = tc.blue(f'{ruri:<60}')
else:
ruri = uri
ruri = f'{ruri:<60}'
v = ' '.join((f'{val:<60}',
src,
ruri,
ilxb[ilx_frag],
differentia))
mmr.append(v)
proto_mmr_1_to_1[uri] = v
src = None
arrr = {**arrr}
arrr_not_1_to_1 = {k:v for k, v in arrr.items() if len(v) > 1}
#arrr_n11_uris = set((u.toPython() for v in arrr_not_1_to_1.values() for u in v))
arrr_n11_uris = set.union(*arrr_not_1_to_1.values())
mmr_1_to_1 = {k:v for k, v in proto_mmr_1_to_1.items() if k not in arrr_n11_uris}
no_uniprot = {k:v for k, v in proto_mmr_1_to_1.items() if k not in uniprot_iuphar}
arrr_n11_text = '\n'.join(f'{k:<15} {sorted(_.toPython() for _ in v)}' for k, v in arrr_not_1_to_1.items())
mmr.sort()
mmr_text = '\n'.join(mmr)
mmr_1_to_1_text = '\n'.join(sorted(mmr_1_to_1.values()))
no_uniprot_text = '\n'.join(sorted(no_uniprot.values()))
